Merge tag 'v0.14.0' into v0.14.0-dev

7e63ef82 · zhuwenwen · 8cbcac5d · b17039bc · 7e63ef82 · 7e63ef82
Commit 7e63ef82 authored Jan 21, 2026 by zhuwenwen
20 changed files
--- a/vllm/model_executor/layers/quantization/quark/quark.py
+++ b/vllm/model_executor/layers/quantization/quark/quark.py
--- a/vllm/model_executor/layers/quantization/quark/quark_moe.py
+++ b/vllm/model_executor/layers/quantization/quark/quark_moe.py
--- a/vllm/model_executor/layers/quantization/rtn.py
+++ b/vllm/model_executor/layers/quantization/rtn.py
--- a/vllm/model_executor/layers/quantization/tpu_int8.py
+++ b/vllm/model_executor/layers/quantization/tpu_int8.py
--- a/vllm/model_executor/layers/quantization/utils/flashinfer_fp4_moe.py
+++ b/vllm/model_executor/layers/quantization/utils/flashinfer_fp4_moe.py
--- a/vllm/model_executor/layers/quantization/utils/flashinfer_utils.py
+++ b/vllm/model_executor/layers/quantization/utils/flashinfer_utils.py
--- a/vllm/model_executor/layers/quantization/utils/fp8_utils.py
+++ b/vllm/model_executor/layers/quantization/utils/fp8_utils.py
--- a/vllm/model_executor/layers/quantization/utils/int8_utils.py
+++ b/vllm/model_executor/layers/quantization/utils/int8_utils.py
--- a/vllm/model_executor/layers/quantization/utils/marlin_utils.py
+++ b/vllm/model_executor/layers/quantization/utils/marlin_utils.py
--- a/vllm/model_executor/layers/quantization/utils/marlin_utils_fp4.py
+++ b/vllm/model_executor/layers/quantization/utils/marlin_utils_fp4.py
--- a/vllm/model_executor/layers/quantization/utils/marlin_utils_fp8.py
+++ b/vllm/model_executor/layers/quantization/utils/marlin_utils_fp8.py
--- a/vllm/model_executor/layers/quantization/utils/quant_utils.py
+++ b/vllm/model_executor/layers/quantization/utils/quant_utils.py
--- a/vllm/model_executor/layers/rotary_embedding/__init__.py
+++ b/vllm/model_executor/layers/rotary_embedding/__init__.py
--- a/vllm/model_executor/layers/rotary_embedding/base.py
+++ b/vllm/model_executor/layers/rotary_embedding/base.py
--- a/vllm/model_executor/layers/rotary_embedding/common.py
+++ b/vllm/model_executor/layers/rotary_embedding/common.py
--- a/vllm/model_executor/layers/rotary_embedding/deepseek_scaling_rope.py
+++ b/vllm/model_executor/layers/rotary_embedding/deepseek_scaling_rope.py
--- a/vllm/model_executor/layers/rotary_embedding/dual_chunk_rope.py
+++ b/vllm/model_executor/layers/rotary_embedding/dual_chunk_rope.py
--- a/vllm/model_executor/layers/rotary_embedding/llama4_vision_rope.py
+++ b/vllm/model_executor/layers/rotary_embedding/llama4_vision_rope.py
--- a/vllm/model_executor/layers/vocab_parallel_embedding.py
+++ b/vllm/model_executor/layers/vocab_parallel_embedding.py
--- a/vllm/model_executor/model_loader/base_loader.py
+++ b/vllm/model_executor/model_loader/base_loader.py